Predicting the weather is one of the most challenging tasks in machine learning due to the fact that physical phenomena are dynamic and riche of events. Moreover, most of traditional approaches to climate forecast are computationally prohibitive.
It seems that a joint research between the Earth System Science at the University of California, Irvine and the faculty of Physics at LMU Munich has an interesting improvement on the scalability and accuracy of climate predictive modeling. The solution is... superparameterization and deep learning.
References
Could Machine Learning Break the Convection Parameterization Deadlock?
State of Artificial Intelligence 2022 (Ep. 196)
Improving your AI by finding issues within data pockets (Ep. 195)
Fake data that looks, feels, and behaves like production.(Ep.194)
Batteries and AI in Automotive (Ep. 193)
Collect data at the edge [RB] (Ep. 192)
Bayesian Machine Learning with Ravin Kumar (Ep. 191)
What is spatial data science? With Matt Forest from Carto (Ep. 190)
Connect. Collect. Normalize. Analyze. An interview with the people from Railz AI (Ep. 189)
History of data science [RB] (Ep. 188)
Artificial Intelligence and Cloud Automation with Leon Kuperman from Cast.ai (Ep. 187)
Embedded Machine Learning: Part 5 - Machine Learning Compiler Optimization (Ep. 186)
Embedded Machine Learning: Part 4 - Machine Learning Compilers (Ep. 185)
Embedded Machine Learning: Part 3 - Network Quantization (Ep. 184)
Embedded Machine Learning: Part 2 (Ep. 183)
Embedded Machine Learning: Part 1 (Ep.182)
History of Data Science (Ep. 181)
Capturing Data at the Edge (Ep. 180)
[RB] Composable Artificial Intelligence (Ep. 179)
What is a data mesh and why it is relevant (Ep. 178)
Environmentally friendly AI (Ep. 177)
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
The Unbelivable Truth - Series 1 - 26 including specials and pilot
Acquired